A cutting tool includes a shaft, and a sensor device disposed in such a manner as to surround a portion of the shaft. The sensor device includes a sensor module including first sensors, a substrate connected to the first sensors, and a wireless communication unit connected to the substrate and configured to transmit a signal including information detected by the first sensors to outside and a housing accommodating the sensor module. A region of the shaft surrounded by the sensor device includes a first region having a shape of a 4n-sided polygon when viewed from a direction in which the rotation axis extends. The plurality of first sensors are arranged on at least two of outer peripheral surfaces of the first region, perpendicular lines of the outer peripheral surfaces passing through the rotation axis and intersecting at 90 degrees.

The present invention provides a method and system for monitoring wear state of milling tools for complex thin-walled components, comprising: taking monotonicity of feature vector as a first index, normalized mutual information of the feature vector and wear vector of the tool as a second index, and a ReLU function of Spearman correlation coefficients between feature vectors and the wear vector of the tool as a third index; according to the above indexes, determining behavior indexes corresponding to each feature vector; characterizing behavior characterizations of signal channels, comparing channel behavior indexes of each signal channel, determining input vectors of model, and training tool state recognition model according to the input vectors; and tool change is determined and performed timely by comparing output wear amount value of the tool by using the model with a threshold value.